JP2014175944A - Television conference apparatus, control method of the same, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a television conference apparatus which can be operated by a user who cannot reach a television conference apparatus and a remote control.SOLUTION: A television conference apparatus has: image pick-up means which acquires image data of one or a plurality of users using a television conference apparatus; audio input means which acquires audio data of the user; analysis means which analyzes at least one of the direction of the user's face and the direction of the user's eyes, from the image data; and estimation means which estimates the intention of operation of the television conference apparatus of the user on the basis of the analysis result of the analysis means. The television conference apparatus performs the operation on the basis of the estimation result obtained by the estimation means.

Description

  The present invention relates to a video conference apparatus, a video conference apparatus control method, and a program.

  2. Description of the Related Art A video conference system that performs a conference with a remote place via a communication network such as the Internet is known. In such a video conference system, it is assumed that a single video conference device is used by a plurality of users, and some users may be located in a place where they cannot reach the video conference device or the remote control. is there. Conventionally, it has been difficult for a user who cannot reach the video conference device or the remote controller to operate the video conference device.

  Further, when the video conference apparatus is operated by voice recognition, there is a risk of erroneous operation due to a speech during the video conference. Patent Document 1 discloses a voice recognition electrical device capable of voice control only when a voice recognition start switch is operated.

The technique disclosed in Patent Document 1 cannot solve the problem of the prior art that a user who is away from the video conference device or the remote controller cannot operate.
Embodiments of the present invention have been made in view of the above-described problems, and an object of the present invention is to provide a video conference apparatus that can be operated by a user who cannot reach a video conference apparatus or a remote controller.

  In order to solve the above-described problem, claim 1 of the present application includes an imaging unit that acquires image data of one or a plurality of users who use a video conference device, a voice input unit that acquires the voice data of the users, Analyzing means for analyzing at least one of the user's face direction and line-of-sight direction from image data, and estimating the user's intention to operate the video conference device based on the analysis result of the analyzing means An estimation unit, and performs the operation based on an estimation result of the estimation unit.

  According to the present embodiment, it is possible to provide a video conference device that can be operated even by a user who cannot reach the video conference device or the remote controller.

It is a figure which shows the structural example of the video conference system which concerns on one Embodiment. It is a hardware block diagram of the video conference apparatus concerning one embodiment. It is a functional block diagram of the video conference apparatus concerning one embodiment. It is a figure which shows the example of arrangement | positioning of the video conference apparatus which concerns on one embodiment. 3 is a flowchart according to the first embodiment. 3 is a flowchart of image processing according to the first embodiment. It is a figure which shows the image of the table for short distance which concerns on 1st Embodiment. It is a figure which shows the image of the table for long distances which concerns on 1st Embodiment. It is a figure which shows the image of the table for medium distances concerning 1st Embodiment. It is a figure which shows the image of the image which the imaging means which concerns on 1st Embodiment acquired. It is a figure which shows the image of the table according to the angle which concerns on 1st Embodiment. 3 is a flowchart of voice recognition means according to the first embodiment. FIG. 3 is a functional configuration diagram of voice recognition means according to the first embodiment. It is a flowchart concerning a 2nd embodiment. It is a figure which shows the example of arrangement | positioning of the video conference apparatus which concerns on other embodiment.

Embodiments of the present invention will be described below with reference to the accompanying drawings.
<System configuration>
FIG. 1 is a diagram illustrating a configuration example of a video conference system 100 according to an embodiment of the present invention. The video conference system 100 includes video conference apparatuses 101, 102, 103 and a server 105 connected to a network 104. For example, the server 105 is responsible for receiving video and audio data from the video conference apparatus 101 and transmitting it to a desired video conference apparatus such as the video conference apparatuses 102 and 103. At this time, the server 105 may have a function of encoding data obtained from the video conference apparatuses 101 to 103 and decoding encoded data obtained from the video conference apparatuses 101 to 103. . Note that the configuration in FIG. 1 is an example, and the number of video conference apparatuses constituting the video conference system may be any number of two or more. Furthermore, a peer-to-peer connection environment that connects video conference apparatuses without using the server 105 may be used.

For example, the video conference apparatuses 101, 102, and 103 can communicate with each other via the server 105 to transmit and receive images and audio. Thereby, the user of the video conference apparatus 101 can hold a video conference with the users of the video conference apparatuses 102 and 103 through images and sounds transmitted and received in real time.
<Device configuration>
(Hardware configuration)
FIG. 2 shows an example of the hardware configuration of the video conference apparatus 101 according to this embodiment. Note that the other video conference apparatuses 102 and 103 constituting the video conference system 100 do not necessarily have the same configuration.

  The video conference apparatus 101 includes a video conference apparatus main body 200 configured by a computer or the like, a display device 210, and one or more microphones 212. The video conference apparatus main body 200 includes a CPU (Central Processing Unit) 201, a memory 202, a control unit 203, an image processing unit 204, an audio processing unit 205, a network interface (hereinafter referred to as network I / F) 206, an image sensor. Interface (hereinafter referred to as image sensor I / F) 207, camera 208, image output interface (hereinafter referred to as image output I / F) 209, audio input / output interface (hereinafter referred to as audio input / output I / F) 214 A speaker 213 and a system bus 214. In addition, the said structure is an example to the last, Comprising: The scope of the present invention is not limited. For example, the camera 208 and the speaker 213 may be provided separately from the video conference apparatus main body 200 or may be built in the display device 210. Further, the video conference apparatus main body 200 may include at least one of the plurality of microphones 212. Further, the image sensor I / F 207 may be included in the image processing unit 204, and the audio input / output I / F 214 may be included in the audio processing unit 205.

  The CPU 201 is an arithmetic device that implements each function of the video conference apparatus 101 by reading a program or data from the memory 202 and executing the processing, for example. The memory 202 is a storage unit such as a random access memory (RAM), a read only memory (ROM), and a hard disk drive (HDD). The memory 202 stores various software necessary for various processes executed by the CPU 201, data, image data, audio data, and the like.

  The control unit 203 controls the entire video conference apparatus 101. The image processing unit 204 performs various image processing on the image data or the image signal. The audio processing unit 205 performs various audio processes on the audio data or the audio signal. Note that the image processing unit 204 and the sound processing unit 205 may include a processor such as a DSP (Digital Signal Processor). A network I / F 206 is an interface for connecting the video conference apparatus 101 to the network 104, and transmits / receives data to / from other video conference apparatuses 102, 103 and the like via the network 104.

The image sensor I / F 207 is an interface that captures an image signal output from the imaging camera 208 as predetermined image data. The display device 210 is a display device such as an LCD (Liquid Crystal Display) monitor or a projector. The display device 210 may include a speaker 213 for outputting sound. The image output I / F 209 is an interface that outputs a communication destination image and various images such as a menu screen and a setting screen to the display device 210.
The voice input / output I / F 211 takes in a voice signal input via a voice input microphone 212 as predetermined voice data. Also, the audio data to be output is converted into an audio signal that can be reproduced by the speaker 213. The system bus 214 transmits an address bus, a data bus, and various control signals.
(Functional configuration)
FIG. 3 is a diagram illustrating a functional configuration of the video conference apparatus 101 according to the present embodiment. The video conference apparatus 101 includes an imaging unit 301, an analysis unit 302, an estimation unit 303, a control unit 304, a voice input unit 305, a voice output unit 306, a voice recognition unit 307, and a volume control unit 308.

  The imaging unit 301 is a unit that acquires image data of a user of the video conference apparatus 101, and includes, for example, the camera 208 of FIG. The analysis unit 302 performs image processing of the image data or the image signal acquired by the imaging unit 301 and analyzes at least one of the face direction and the line of sight for each user of the video conference apparatus 101. Based on the analysis result of the analysis unit 302, the estimation unit 303 estimates the intention of each user to operate the video conference apparatus 101. The analysis unit 302 and the estimation unit 303 are included in, for example, the image processing unit 204 in FIG. Further, the analysis unit 302 and the estimation unit 303 may be realized by a program that operates on the CPU 201 or the like.

  The control unit 304 is a unit that controls the video conference apparatus 101 based on the estimation result of the estimation unit 303, and includes, for example, a program that operates on the control unit 203 and the CPU 201 in FIG. Note that, for example, the estimation unit 303 or the like may control the voice recognition unit 307 or the like without using the control unit 304 as necessary. The voice input means 305 is means for acquiring voice data of a user of the video conference apparatus 101 and includes, for example, the microphone 212 of FIG. The voice recognition unit 307 performs voice processing on the voice data or voice signal acquired by the voice input unit 305, compares the voice data or voice signal with a pre-registered word pattern and control content, and recognizes the control content. The voice recognition unit 307 is included in, for example, the voice processing unit 205 in FIG. Alternatively, the function may be realized by a program operating on the CPU 201 or the like.

  The audio output unit 306 is a unit that performs audio output of the video conference apparatus 101, and includes, for example, the speaker 213 of FIG. The volume control unit 308 adjusts the volume output from the audio output unit 306 and the level of the audio input from the audio input unit 305 under the control of the control unit 304, the voice recognition unit 307, and the like. The volume control unit 308 is included in, for example, the voice input / output I / F 211 and the voice processing unit 205 shown in FIG.

  Next, FIG. 4 shows an example of the arrangement of each unit when the video conference apparatus 101 is used. On the conference table 406, as shown in FIG. 4, a video conference apparatus main body 200 having a camera 208, a display device 210, and a plurality of microphones 212a and 212b are arranged. In addition, it is assumed that users 401, 402, 403, and 404 are sitting around the conference table 406 at a position where the display device 210 and the camera 208 can be seen. Furthermore, the video conference apparatus 101 may further include a remote controller 405 for operating the video conference apparatus 101.

  The video conference apparatus 101 estimates the intention of each user's operation based on the face direction or line-of-sight direction of each user with respect to the camera 208. For example, when the user's face direction or line of sight faces the camera 208, it is determined that the user intends to operate the video conference apparatus 101 by voice. At this time, the video conference apparatus 101 starts voice recognition processing and controls the video conference apparatus 101 corresponding to the recognition result.

With the above configuration, for example, in FIG. 4, even the users 401 and 403 away from the video conference apparatus main body 200 and the remote controller 405 can operate the video conference apparatus 101 by voice by giving instructions to the camera 208. Can do.
<Description of operation>
Next, the operation of the video conference apparatus 101 according to this embodiment will be described.
[First Embodiment]
FIG. 5 shows a flowchart according to the first embodiment. The video conference apparatus 101 acquires image data of one or a plurality of users by the imaging unit 301. (Step S501) Next, the analysis unit 302 analyzes at least one of the face direction and the line of sight for each user from the image data. (Step S502)
It should be noted that the analysis of each user's face direction and line-of-sight direction may be performed by a general face recognition technique or line-of-sight analysis technique. Here, only an outline of an example of the face recognition technique and the line-of-sight analysis technique will be described. First, with regard to the orientation of the user's face, components such as the face, eyes, nose and mouth of each user are extracted from the image data acquired by the imaging unit 301 by applying, for example, a pattern recognition technique. Then, the orientation of the face is determined from the positional relationship between the extracted components. Alternatively, the face orientation may be calculated from the positional relationship and angle of the eyes. As for the line-of-sight analysis, for example, the position of each user's iris is detected, and the distance from each user's eye, nose, mouth and other components to the iris, and the orientation of the face, Analyzes the user's line of sight.

  These methods are merely examples and do not limit the scope of the present invention. Other methods may be used to detect the face direction and line-of-sight direction of each user.

  Next, the estimation unit 303 estimates the intention of each user's operation based on the analysis result of the analysis unit 302. For example, in FIG. 4, each user is normally viewing the display device 210 during a video conference. That is, during a video conference, each user looks at the display device 210 in order to confirm the other party displayed on the display device 210, the presented material, and the like. In this situation, when one of the users turns his eyes to the camera 208 or the video conference apparatus main body 200 and speaks, the intention is not to speak to the video conference participant of the communication destination but to operate the video conference apparatus 101. it seems to do. Therefore, in the present embodiment, the estimation unit 303 determines whether or not the direction of each user's face or line of sight with respect to the camera 208 faces the direction of the camera 208 or the video conference apparatus main body 200. (Step S503) When the direction of the face or the line of sight of at least one of the users faces the direction of the camera 208 or the video conference apparatus main body 200, the estimating means 303 uses the voice recognition by the user. It is determined that the operation of the conference apparatus 101 is intended.

  Further, as a more preferable example, it is used when the user's face direction or line-of-sight direction is facing the direction of the camera 208 or the video conference apparatus body 200 for a predetermined time (for example, 5 seconds). It may be determined that the person intends the operation by voice recognition. Accordingly, it is possible to prevent the voice recognition process from being erroneously started when the user happens to look at the camera 208 or the video conference apparatus main body 200.

  When the estimation unit 303 determines that the user's face direction or line-of-sight direction is facing the camera 208, the voice recognition unit 307 performs voice recognition processing on the voice data acquired by the voice input unit 305. . (Step S504) Thereafter, the video conference apparatus 101 is controlled based on the result of the voice recognition process. (Step S505) The voice processing will be described later.

  As a preferred example, while the voice recognition means 307 is performing voice recognition processing, it is preferable to have means for notifying each user by a display, a voice message, a sound effect or the like. Accordingly, each user can know that the video conference apparatus 101 is performing the voice recognition processing, and therefore can refrain from a statement that causes an erroneous operation. On the other hand, when the estimation unit 303 determines that the orientation of the user's face or the direction of the line of sight does not match the direction of the camera 208 or the imaging unit 301, the process returns to step S501 and the processing of steps S501 to S503 is performed again. Do.

With the above operation, each user can operate the video conference apparatus 101 by voice control without operating the video conference apparatus 101 or the remote controller 405.
(Image processing)
Here, an example of the image processing of the analysis unit 302 and the estimation unit 303 will be described with a specific example. FIG. 6 is a flowchart illustrating an example of image processing operations of the analysis unit 302 and the estimation unit 303. When a human face is detected in the image data acquired by the imaging unit 301, the analysis unit 302 acquires the face direction of the user. (Step S601) In addition, the distance between the imaging unit 301 and the user is acquired from the ratio of the face area in the imaging range at the same time. (Step S602) Furthermore, the angle between the camera 208 and the user or the camera 208 and the video conference apparatus body 200 is acquired as necessary. (Step S603)
Next, based on the acquired distance from the user and the angle between the camera 208 and the user or the video conference apparatus main body 200, the estimation unit 303 determines the position of the face of the camera 208 relative to the camera 208 and the position of the camera 208. A table to be used is selected from a plurality of tables indicating the relationship with the reference face direction, which is the face direction when facing in the direction. (S604)
Here, the table will be described. FIG. 7 shows an image of a short distance table. The four squares correspond to the face positions in the image acquired by the camera 208. In addition, for each square, reference face direction data indicating the face direction when the face faces the camera 208 is stored. Therefore, for example, when the face direction of the person shown in the upper left of the image acquired by the camera 208 matches the reference face direction of the square in the first row of column A in FIG. It can be determined that the camera 208 is facing.

  Note that the ratio of the area of the face in the imaging range varies depending on the distance between the camera 208 and the user. For example, when the distance between the camera 208 and the use is far, the ratio of the area of the face to the imaging range is small, so a long distance table as shown in FIG. 8 is used. . On the other hand, if the camera 208 is close to the user and the face does not fit in the squares of the long distance table, the medium distance table shown in FIG. 9 or the short distance table shown in FIG. 8 is selected. To do.

  For example, assume that the image data acquired by the imaging unit 301 is as shown in FIG. Here, when determining the orientation of the face of the person shown on the left front, it is preferable to select the medium distance table in FIG. 9 from the area of the face. In this case, since the face position corresponds to the A column and the second row of the intermediate distance table in FIG. 9, the corresponding reference face direction can be acquired from the table. If the reference face direction matches the face direction of the person shown in the left front of FIG. 10, it can be determined that the person is facing the camera 208.

  Further, the position of the face of the image data and the orientation of the face when facing the direction of the camera 208 also vary depending on the angle between the user and the camera 208. For example, when the camera 208 is installed in an oblique direction with respect to the user, for example, as shown in FIG. 11, the face direction when the user looks at the camera 208 is considered to change. . Therefore, it is preferable to prepare a plurality of tables according to the angle between the user and the camera 208.

  Note that the angle between the user and the camera 208 may be set when the video conference apparatus 101 is always installed in a specific conference room. Further, when the position of the video conference apparatus main body 200 is fixed and the angle between the video conference apparatus main body 200 and the camera 208 can be changed, it may be obtained based on the angle between the video conference apparatus main body 200 and the camera 208. Alternatively, at the start of the video conference, one or a plurality of users may face the camera 208 and perform a setting operation to select an optimal table. Further, the analysis unit 302 may calculate based on the face direction when the user is viewing the display device 210 during a TV conference.

Note that the face on the image data may extend over a plurality of areas of the table. In this case, for example, the processing may be performed assuming that the face is in the area where the center of the face is contained. Returning to FIG. Continue the explanation. In step S604, the estimation unit 303 selects a table to be used, and then determines a reference face direction, which is information on the face direction when viewing the direction of the camera 208 corresponding to the face position, from the table. (Step S605) Next, it is compared whether or not the user's face direction matches the reference face direction. (Step S606) Here, “match” is not only the case where 100% match completely, but it can be determined that the difference is within a predetermined range and is substantially in the same direction. Including cases.

  Here, when the user's face direction matches the reference face direction, the voice recognition process is started. (S607) On the other hand, if the user's face direction does not match the reference face direction, the process returns to step S601 and the process is performed again.

As described above, according to the image processing in FIG. 6, it is possible to perform the processing only by analyzing the face direction without performing the user's line-of-sight analysis. The above operation is merely an example, and does not limit the scope of the present invention. For example, instead of preparing in advance a plurality of tables corresponding to the angle between the camera 208 and the user, a table corresponding to the angle may be calculated based on a reference table. Alternatively, instead of having a plurality of tables corresponding to distances and angles, for example, at the start of a conference, each user faces the camera 208 and performs a predetermined operation to create a new table. There may be.
(Audio processing)
Next, the voice recognition process of the voice recognition unit 307 will be described with a specific example. FIG. 12 shows a flowchart of the speech recognition process in the first embodiment. FIG. 13 shows a functional configuration of the voice recognition unit 307. In FIG. 13, the speech recognition unit 307 includes an acoustic analysis unit 1301, a word recognition unit 1302, a control recognition unit 1303, a word pattern storage unit 1304, and a word-control signal correspondence storage unit 1305. The acoustic analysis unit 1301 performs acoustic analysis of the voice data or voice signal acquired by the voice input unit 305. (Step 1201 and Step S1202 in FIG. 12) The speech data or speech signal analyzed by the acoustic analysis unit 1301 is collated with the word pattern stored in the word pattern storage unit 1304 in the word recognition unit 1302. (Step S1203 in FIG. 12)
When the voice data or voice signal analyzed by the acoustic analysis unit 1301 matches the word pattern stored in the word pattern storage unit 1304, the matched word information is input to the control recognition unit 1303. The control recognition unit 1303 determines or executes the control content corresponding to the input word information based on the information of the combination of the word information and the control content stored in the word-control signal correspondence storage unit 1305. With the above configuration, the voice recognition unit 307 analyzes the voice data or voice signal input from the voice input unit 305, determines the presence or absence of control content corresponding to the input voice data or voice signal, and the corresponding control content. If there is, a control signal corresponding to the control content corresponding to the input audio data is transmitted. (Step S1204 in FIG. 12)
With the above operation, when the voice input from the voice input unit 305 matches the voice data registered in advance, the video conference apparatus 101 is operated by voice.

  As described above, according to this embodiment, a user who cannot reach the video conference apparatus main body 200 or the remote controller 405 can operate the video conference apparatus 101. In addition, when an operation is required, the voice recognition process can be activated by facing the camera 208 or the video conference apparatus main body 200 provided with the camera 208. Therefore, an unintended operation is performed due to a speech during the video conference. Can be effectively prevented. Further, by providing a means for notifying the user of the fact while the voice recognition means 307 is performing the voice recognition process, it is possible to more effectively prevent a malfunction due to a speech during the meeting.

In addition, the said structure is an example to the last, Comprising: The scope of the present invention is not limited. For example, the word pattern storage unit 1304 and the word-control signal correspondence storage unit 1305 in FIG. 13 may be included in the memory 202 in FIG. 2 or on the cloud (for example, a server on a network such as the Internet). You may have. Further, in step S1204 in FIG. 12, the control means 304 in FIG. 3 may control the video conference apparatus 101 instead of the control recognition means 1303 sending a control signal.
[Second Embodiment]
Next, a second embodiment will be described.
In FIG. 4, for example, when the user 402 is talking to the user 401, there is no intention to talk to the user of the video conference device as the communication destination, and the contents that the user wants to talk only to the user 401 are displayed. It is possible to talk. Conventionally, in such a case, even when the user 402 is speaking in a low voice, the gain of the microphone 212a is automatically increased, so that the conversation content is unintentionally transmitted to the video conference user of the communication destination. There was a case. The present embodiment addresses such a problem.

  FIG. 14 shows a flowchart according to the present embodiment. The operations from step S501 to step S505 shown in FIG. 5 are the same as those in the first embodiment. Here, the description will focus on the differences from the first embodiment.

In step S <b> 503, when it is determined that the orientation of the user's face or the direction of the line of sight does not match the direction of the imaging unit 301, the orientation of the user's face or the direction of the line of sight is previously set with respect to the direction of the imaging unit 301. Determine if it is within the specified range. (Step S1401)
If the direction of the face or the line of sight of at least one of the users is not within a predetermined range with respect to the direction of the imaging unit 301, the user adjusts the volume of the microphone 212a and the microphone 212b. It is determined that it is intended, and the volume of the microphone 212a and the microphone 212b is automatically adjusted. (Step S1402)
Specifically, the video conference apparatus 101 adjusts the volume of the audio signal transmitted to the communication destination video conference apparatuses 102 and 103 based on the audio input level from the microphone 212a and the microphone 212b.

  For example, if there is an audio input level greater than a predetermined value from the microphone 212a, it is considered to be a message to the user of the video conference device at the communication destination, so the volume of the communication destination is not adjusted. On the other hand, when an audio signal smaller than a predetermined value is input from the microphone 212a, it is determined that the message is not a message to the video conference device user of the communication destination, and the volume of the audio signal to the communication destination is lowered. Or mute. Further, when there is no voice input from the microphone a, it is determined that the user has simply looked in another direction, and it is not necessary to adjust the voice to the communication destination.

  The microphone 212b is similarly controlled. Thus, a conversation with a low voice does not reach the user at the communication destination, and a speech or the like to the communication destination with a high voice can be delivered to the user at the communication destination as usual.

  On the other hand, if it is determined in step S1401 that the user's face orientation or line-of-sight direction is within a predetermined range with respect to the direction of the imaging unit 301, the process returns to step S501 and continues.

  Note that the “predetermined range” in step S1401 can be arbitrarily set according to the request of the system or the user. For example, the range that can be detected by both of the eyes of the user by the estimation unit 303 may be set as the predetermined range. Further, when the estimation unit 303 can detect the face direction or line-of-sight direction of the user, it may be determined that the face direction or line-of-sight direction is within the predetermined range. Alternatively, when the estimation unit 303 determines that the user has turned sideways beyond a predetermined angle with respect to the camera 208, the estimation unit 303 may determine that the user is not within the predetermined range.

As described above, according to the present embodiment, when the user is speaking with a small voice, it is possible to reduce the unintentional transmission of the conversation contents to the video conference device user of the communication destination.
[Other embodiments]
As the camera 208 for acquiring the image data of each user, a camera for photographing a video conference participant as provided in a conventional video conference device can be used. However, a camera 208 may be provided separately from the camera for the video conference participant (for example, the camera 208 in FIG. 14). In this case, since the image data acquired by the camera 208 is not displayed at the communication destination or the like in this case, for example, a fisheye lens or a 360-degree lens for panorama can be used as the lens of the camera 208.

DESCRIPTION OF SYMBOLS 101 Video conference apparatus 200 Video conference apparatus main body 210 Display apparatus 212, 212a, 212b Microphone 208 Camera 301 Imaging means 302 Analysis means 303 Estimation means 305 Voice input means 307 Voice recognition means

Japanese Patent Laid-Open No. 11-202892

Claims (10)

Imaging means for acquiring image data of one or a plurality of users using the video conference device;
Voice input means for acquiring voice data of the user;
Analyzing means for analyzing at least one of the face direction and the line-of-sight direction of the user from the image data;
An estimation means for estimating an intention of the user to operate the video conference device based on an analysis result of the analysis means,
A video conference apparatus that performs the operation based on an estimation result of the estimation means.   The estimation unit estimates that the video conference device is intended to be operated when a face direction or a line-of-sight direction of at least one of the users faces a direction of the imaging unit. The video conference apparatus described in 1.   A table showing a relationship between a face position with respect to the image pickup means and a direction of the face or a line of sight when the image pickup means is viewed at the face position; and at least one face of the user 3. The video conference according to claim 1, wherein the video conference device estimates that the video conference device is intended to be operated when the orientation or the gaze direction is a face orientation or a gaze direction included in the table. apparatus.   The video conference apparatus according to claim 3, comprising a plurality of the tables corresponding to a distance between the imaging unit and the user.   The video conference apparatus according to claim 3, further comprising a plurality of the tables corresponding to an angle between an imaging direction of the imaging unit and the user.   The video conference apparatus according to claim 1, wherein an intention of operating the video conference apparatus is an operation of the video conference apparatus by voice.   The estimation unit obtains the voice acquired from the voice input unit when the face direction or the line-of-sight direction of at least one of the users is not within a predetermined range with respect to the direction of the imaging unit. The video conference apparatus according to claim 1, wherein it is estimated that the volume control is intended.   The volume control of the voice acquired from the voice input unit is performed based on a direction of a face or a line of sight of at least one of the users and a voice input level from the voice input unit. Video conferencing equipment. Acquiring image data of one or more users of the video conference device;
Analyzing at least one of face orientation and line of sight for each of the users from the image data;
Estimating the user's intention to operate the video conference device based on the analysis result of the analysis means;
Performing the operation based on an estimation result of the estimation means;
A control method for a video conference apparatus. On the computer,
A procedure for acquiring image data of one or more users of the video conference device;
A procedure for analyzing at least one of the orientation and line of sight of each of the users from the image data;
A procedure for estimating an intention of an operation of each of the users on the video conference device based on an analysis result of the analysis means;
A procedure for performing the operation based on an estimation result of the estimation means;
A program for running

Images